{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T13:21:37Z","timestamp":1725456097895},"publisher-location":"London","reference-count":14,"publisher":"Springer-Verlag","isbn-type":[{"type":"print","value":"3540199055"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/bfb0027599","type":"book-chapter","created":{"date-parts":[[2005,11,19]],"date-time":"2005-11-19T05:13:10Z","timestamp":1132377190000},"page":"245-254","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcement learning of assembly robots"],"prefix":"10.1007","author":[{"given":"Boo-Ho","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haruhiko","family":"Asada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"20_CR1","unstructured":"B.-H. Yang and H. Asada, \u201cAdaptive Reinforcement Learning and Its Application to Robot Control\u201d, DSC-Vol. 49, Advances in Robotics, Mechatronics, and Haptic Interfaces, ASME Winter Annual Meeting, 1993"},{"issue":"2","key":"20_CR2","first-page":"91","volume":"99","author":"D. E. Whitney","year":"1977","unstructured":"D. E. Whitney, \u201cForce Feedback Control of Manipulator Fine Motions\u201d, ASME J. of DSMC, vol. 99, no. 2, pp 91\u201397, 1977","journal-title":"ASME J. of DSMC"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"J. K. Salisbury, \u201cActive Stiffness Control of a Manipulator in Cartesian Coordinates\u201d, Proc. of the 19th IEEE Conf. on Decision and Control, pp. 95\u2013100, 1980","DOI":"10.1109\/CDC.1980.272026"},{"issue":"6","key":"20_CR4","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1109\/TSMC.1981.4308708","volume":"SMC-11","author":"M. T. Mason","year":"1981","unstructured":"M. T. Mason, \u201cCompliance and Force Control for Computer Controlled Manipulators\u201d, IEEE Trans. on Systems, Man, and Cybernetics, vol. SMC-11, no. 6, pp. 418\u2013432, 1981","journal-title":"IEEE Trans. on Systems, Man, and Cybernetics"},{"issue":"2","key":"20_CR5","first-page":"126","volume":"102","author":"M. Raibert","year":"1981","unstructured":"M. Raibert and J. Craig, \u201cHybrid Position\/Force Control of Manipulators\u201d, ASME J. of DSMC, vol. 102, no. 2, pp. 126\u2013133, 1981","journal-title":"ASME J. of DSMC"},{"key":"20_CR6","first-page":"1","volume":"107-1","author":"N. Hogan","year":"1985","unstructured":"N. Hogan, \u201cImpedance Control: An Approach to Manipulation: Part I\u2013III\u201d, ASME J. of DSMC, vol. 107-1, pp. 1\u201323, 1985","journal-title":"ASME J. of DSMC"},{"key":"20_CR7","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/ROBOT.1993.292129","volume":"2","author":"S. Hirai","year":"1993","unstructured":"S. Hirai and K. Iwata, \u201cDerivation of Damping Control Parameters Based on Geometric Model\u201d, Proc. of IEEE Int. Conf. on Robotic and Automation, vol. 2, pp. 87\u201392, 1993","journal-title":"Proc. of IEEE Int. Conf. on Robotic and Automation"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"M. A. Peshkin, \u201cProgrammed Compliance for Force Corrective Assembly\u201d, IEEE Trans. on Robotics and Automation, Vol. 6, No. 4, August, 1990","DOI":"10.1109\/70.59358"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"H. Asada, \u201cTeaching and Learning of Compliance Using Neural Nets: Representation and Generation of Nonlinear Compliance\u201d, Proc. of IEEE Int. Conf. on Robotics and Automation, 1990","DOI":"10.1109\/ROBOT.1990.126167"},{"issue":"5","key":"20_CR10","first-page":"835","volume":"13","author":"A. G. Barto","year":"1983","unstructured":"A. G. Barto, R. S. Sutton and C. W. Anderson, \u201cNeuronlike Elements That Can Solve Difficult Learning Problems\u201d, IEEE Trans. of Systems, Man, and Cybernetics, vol. 13(5), p.p. 835\u2013846, 1983","journal-title":"IEEE Trans. of Systems, Man, and Cybernetics"},{"key":"20_CR11","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1016\/0893-6080(90)90056-Q","volume":"3","author":"V. Gullapalli","year":"1990","unstructured":"V. Gullapalli, \u201cA Stochastic Reinforcement Learning Algorithm for Learning Real-Valued Functions\u201d, Neural Networks, Vol. 3, pp. 671\u2013692, 1990","journal-title":"Neural Networks"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"R. J. Williams, \u201cSimple Statistical Gradient-Following Algorithm for Connectionist Reinforcement Learning\u201d, Machine Learning, 8, 1992","DOI":"10.1007\/978-1-4615-3618-5_2"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"P. J. Werbos, \u201cGeneralization of Back Propagation with Application to a Recurrent Gas Market Model\u201d, Neural Networks, 1, 1988","DOI":"10.1016\/0893-6080(88)90007-X"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"M. I. Jordan and D. E. Rumelhart, \u201cForward Models: Supervised Learning with a Distal Teacher\u201d, Cognitive Science, 16, 1992","DOI":"10.1207\/s15516709cog1603_1"}],"container-title":["Lecture Notes in Control and Information Sciences","Experimental Robotics III"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/BFb0027599.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,9]],"date-time":"2020-12-09T16:56:52Z","timestamp":1607533012000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/BFb0027599"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["3540199055"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/bfb0027599","relation":{},"subject":[]}}